Python web自动化爬虫-selenium/处理验证码/Xpath

# coding:utf-8
import time
import random
from time import sleep
from csv import writer
from selenium import webdriver
from selenium.webdriver.common.by import By
from chaojiying import Chaojiying_Client
from selenium.webdriver import ActionChains


driver = webdriver.Chrome()

#打开网页
def open_web(search_name):
    driver.get("https://www.izaiwen.cn/pro/sonE-stwE08?psnname={}".format(search_name))
    time.sleep(6)
#加载cookie
#    with open("cookies.json", "r") as file:
#        cookies = json.load(file)
    cookies = [{'name': 'HMACCOUNT', 'value': 'xxxxxxxxx'},
    {'name': 'heiheihei', 'value': 'xxxxxxxxx'},
    {'name': 'hahaha', 'value': 'xxxxxxx'},
    {'name': '_', 'value': 'xxxxxxxxxxx'},
    {'name': 'acw', 'value': 'xxxxxxxxxxxx'},
    {'name': 'cer', 'value': 'xxxxxxxxxx'},
    {'name': 'ession', 'value': 'xxxxxxxxxx'},
    {'name': 'userId', 'value': 'xxxxx'},
    {'name': 'uuid', 'value': 'xxxxxxxxxxxxxxxxxxx'},
    ] 
    for cookie in cookies:
        driver.add_cookie(cookie)
    time.sleep(5)
    driver.refresh()
    time.sleep(random.randrange(5,10))

#检测是否在验证码页面
def check_condition():
    header=driver.title#提取页面标题
#    header=driver.find_element(By.XPATH,'/html/head/title').text  此方法无效，只能取出空字符串
    print(header)
    if header == '请完成安全验证': #如果在验证码页面返回f值
        return 'f'
    else:
        return 't'

#基于xpath定位标签获取数据
def get_information():
    parent_element=driver.find_elements(By.XPATH,'.//div[@class="item-box layui-card "]')
    for child_element in parent_element:
        target_element=child_element.find_elements(By.XPATH,'.//div[@class="layui-col-xs4"]')
        print(name)
        info=''
        for n in target_element:
            info+=n.text#提取标签中的数据
            info+=','
        print(info)
        list_data=[name,info]
        #保存数据
        with open("信息.csv", "a", newline="") as f_object:
            writer_object = writer(f_object)
            writer_object.writerow(list_data)
        time.sleep(5)
#自动识别验证码并提交至超级鹰打码平台识别
def anti_anti_spider():
    #找到包含验证码的元素
    img=driver.find_element(By.XPATH,'.//div[@id="aliyunCaptcha-window-embed"]')
    #对此元素进行截图
    img.screenshot('D:/SeleniumX/yzm.png')
    #由于新版本的selenium的点击定位是从元素中心点开始，因此计算元素的尺寸来使点击从左上角开始
    img_half_width = float(img.rect['width'])/2
    img_half_height = float(img.rect['height'])/2
    #初始化超级鹰代码，需要从其官网下载代码放到此文件相同文件夹中并导入
    chaojiying = Chaojiying_Client('', '', '')#账号，密码，软件ID
    #提交到平台并获得结果
    im = open('D:/SeleniumX/yzm.png', 'rb').read()
    yzm_result=chaojiying.PostPic(im, 9101)['pic_str']
    time.sleep(10)
    print(yzm_result)
#    for index in result.split('|'): #以"|"进行分割，得到一个列表，并循环出每一个字的坐标，在这里因为只返回一个结果所以不需要
    x = float(yzm_result.split(',')[0]) # 得到x轴的坐标
    y = float(yzm_result.split(',')[1]) # 得到y轴的坐标
    #使用动作链模拟点击操作
    action = ActionChains(driver) #创建动作链,y).click().perform()
    action.move_to_element_with_offset(img,x-img_half_width,y-img_half_height).click().perform()
    time.sleep(10)

    

#主程序
list_name=[]#需要爬取的人名，用于构建页面url
for name in list_name:
    open_web(name)#打开该网页
    flag=check_condition()#检测是否触发了验证码
    print(flag)
    if flag == 'f':#若触发了验证码，开始识别并点击验证码
        time.sleep(30)
        anti_anti_spider()
        time.sleep(15)
        get_information()
    else:
        time.sleep(5)
        get_information()
    time.sleep(random.randrange(10,30))
    print(name)